aimeri/spoomplesmaxx-mockingbird-36B
Full fine-tune vs ByteDance-Seed/Seed-OSS-36B-Base-woSyn. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 19/129, MLP 192/192, Attention 446/448, lm_head 1/1
3 derivatives checked
- mradermacher/spoomplesmaxx-mockingbird-36B-i1-GGUF: Quantization
- mradermacher/spoomplesmaxx-mockingbird-36B-GGUF: Quantization
- aimeri/spoomplesmaxx-mockingbird-36B-i1-GGUF: Quantization